© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130272
    Prev
    Next
    INDEX
    Explanations

    glow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    संहार
    0.47
    个人的
    0.42
    济
    0.39
     کاروب
    0.38
     ekonomik
    0.38
     एवरी
    0.38
    记得
    0.38
     економі
    0.37
    വുമായ
    0.36
     രാ
    0.36
    POSITIVE LOGITS
     perfectly
    0.39
     Apparently
    0.38
     niin
    0.38
    aldi
    0.38
    ﾐ
    0.37
    omini
    0.37
    อาจ
    0.37
     apparently
    0.37
    誂
    0.36
     чрезвы
    0.36
    Activations Density 0.000%

    No Known Activations